It is well-known that if $d,n \in \mathbb{N}^*$ and $d \mid n$ then $2^d -1 \mid 2^n - 1$.
Is the reciprocal true ? With a Python program it shows that it may be true (didn't found any counterexample) but I haven't been able to prove it.
My attempt :
By contraposition, if $d \nmid n$ then exists $(q,r)\in\mathbb{N} \times \mathbb{N}^*$ such that $n=dq+r$. Then :
$$2^n-1 = 2^{dq}2^r -1$$
And I tried to watch what's happening modulo $2^d-1$ but it wasn't succesful.
If anybody knows what to do I would be grateful.